如何在TensorFlow中仅为训练阶段定义图层？

3 回答

• 0

  您可能希望使用"tf.cond" control_flow操作执行此操作 . https://www.tensorflow.org/api_docs/python/control_flow_ops/control_flow_operations#cond

  回复于 2024-05-03T15:30:26+08:00
• 1

  我认为你可以使用带有tf.cond（）的布尔占位符 . 像这样：

  train_phase = tf.placeholder(tf.bool, [])
  x = tf.constant(2)
  def f1(): return tf.add(x, 1)
  def f2(): return tf.identity(x)
  r = tf.cond(train_phase, f1, f2)
  sess.run(r, feed_dict={train_phase: True})  # training phase, r = tf.add(x, 1) = x + 1
  sess.run(r, feed_dict={train_phase: False})  # testing phase, r = tf.identity(x) = x
  

  回复于 2024-05-03T15:30:26+08:00
• 1

  我想你可以通过 if 这样做

  Train = False
  
  x = tf.constant(5.)
  y = x + 1
  if Train:
      y = y + 2
  y = y + 3
  
  with tf.Session() as sess:
      res = sess.run(y) # 11 if Train else 9
  

  回复于 2024-05-03T15:30:26+08:00